asgeirtj/system_prompts_leaks
This repository provides a collection of extracted system prompts from various large language models (LLMs) including Anthropic's Claude, OpenAI's ChatGPT, Google's Gemini, and xAI's Grok, updated ...
Awesome AI Agents › Prompt Libraries
dzhng/deep-seek
DeepSeek is an experimental architecture for a large language model (LLM) powered internet-scale retrieval engine designed to process vast amounts of sources to compile a comprehensive list of entities rather than just providing a single correct answer. Unlike traditional research agents that function as answer engines, DeepSeek focuses on gathering extensive data and presenting it in a structured table format with enriched columns representing additional relevant information about each entity. The system operates through a multi-step research pipeline involving planning, searching, extracting, and enriching data. Initially, the planner breaks down the user query to define the type of entities and the structure of the resulting table. The search step employs both keyword and neural search techniques to find relevant content, leveraging services like Exa.ai. The extraction phase uses a novel method where special tokens are inserted between sentences to efficiently identify and extract relevant content ranges using LLMs. Finally, an internal answer agent enriches the data by filling in detailed information for each entity, which is the most time-consuming but crucial part of the process. The engine also generates confidence scores for the data, highlighting cells with low confidence to indicate potential conflicts or guesses. DeepSeek supports running locally with environment variables for API keys from Anthropic and Exa, and it offers a developer-friendly setup with multiple package managers. Future enhancements include better sorting and ranking of entities, improved entity resolution to avoid duplicates, enhanced source verification, deep browsing capabilities for thorough content exploration, and real-time streaming of data enrichment in the user interface. This project is ideal for users and developers interested in advanced data retrieval and entity extraction at scale, providing a powerful tool for comprehensive research and data aggregation tasks.
https://github.com/dzhng/deep-seek
Also in Prompt Libraries
HKUDS/RAG-Anything
RAG-Anything is a next-generation all-in-one multimodal Retrieval-Augmented Generation system that processes and queries diverse document content including text, images, tables, and equations within a unified framework.
dzhng/deep-research
Open Deep Research is an AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models to generate comprehensive markdown reports.
dottxt-ai/outlines
Outlines is an open-source tool that enables structured text generation with large language models, ensuring predictable and schema-compliant outputs for various applications.
microsoft/RD-Agent
RD-Agent is an open-source R&D automation tool by Microsoft designed to automate and enhance industrial research and development processes focused on data and models using AI.
arcee-ai/mergekit
mergekit is a toolkit for efficiently merging pre-trained large language models using various algorithms, supporting CPU and GPU execution, and enabling creation of versatile merged models with maintained inference costs.
icip-cas/PPTAgent
PPTAgent is an innovative system that automatically generates and evaluates high-quality presentations from documents using a two-phase approach and a comprehensive multi-dimensional evaluation framework.
serenakeyitan/awesome-notebookLM-prompts
A curated collection of NotebookLM and Kael.im slide prompts designed to generate presentation-ready decks from various content types.